Hybrid Load Identification Model Based on Grey Wolf Optimization Algorithm
LV Xinwei, Zhiren Ren, Bo Tang, Liu Hui, Yang Rui, Wu Haiping · 2019
Non-intrusive load monitoring is important for the development of smart grids. In order to get the load status and power consumption information of each device, single classifiers such as the support vector machines, the MLP neural networks and the extreme learning machines are widely used to identify the appliances. But the single classifiers are faced with the risk of local optimum and overfitting. In order to improve the recognition accuracy of the single classic classifiers, a hybrid identification model based on grey wolf optimization algorithm is proposed in this paper. The experimental results based on the actual measured data verified that the recognition accuracy of the proposed method is significantly higher than that of the single classical classification models.